© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 189
    Prev
    Next
    INDEX
    Explanations

    mentions of stating, speaking, or saying something

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UGE
    -0.54
    ADORA
    -0.52
     Réponses
    -0.52
     StringVar
    -0.52
     виправивши
    -0.52
    adne
    -0.50
    NewRow
    -0.50
    plona
    -0.48
    ]-->
    -0.48
     downvoted
    -0.48
    POSITIVE LOGITS
     goodbye
    0.98
     aloud
    0.85
     words
    0.81
     loudly
    0.74
     “
    0.69
     "
    0.68
     WORDS
    0.68
     verbally
    0.67
     مشين
    0.66
     jokingly
    0.65
    Activations Density 1.147%

    No Known Activations